Human-in-the-Loop Escalate

Long-running agent loops fail in a specific way when they meet a question they can't answer: they guess. The guess ships, the next session builds on it, and by the time a human looks the divergence is three commits deep. This skill is the release valve, when the agent is stuck, it stops and asks, cleanly, in a shape the human can act on.

Trigger, escalate when any of these are true

• Ambiguous spec. PROMPT.md admits two implementations and the choice changes user-visible behavior.
• Missing credential. A required env var, API key, or config file is absent, and there is no sanctioned way for the agent to create one.
• Destructive action needing approval. Dropping a table, force-pushing, deleting user data, spending money, sending mail to real recipients.
• 3+ consecutive /verify failures on the same task. The loop is thrashing. Stop and get a human eye before the fourth attempt.
• External dependency down. A third-party service the feature needs is unreachable and no offline path exists.

If none of the above hold, do not escalate. Guessing is bad; escalating on a solvable problem is also bad (it trains humans to ignore the channel).

Primary action, call the human via the configured channel

Read LOOPKIT_HITL_CHANNEL. Supported values:

Value	Shape
telegram	POST to https://api.telegram.org/bot$LOOPKIT_HITL_TELEGRAM_TOKEN/sendMessage with chat_id=$LOOPKIT_HITL_TELEGRAM_CHAT, text=<question + repo + short context>.
slack	POST JSON {"text": "..."} to $LOOPKIT_HITL_SLACK_WEBHOOK (incoming-webhook URL).
dial	Run $LOOPKIT_HITL_DIAL_CMD with the message on stdin. Whatever the operator wired up, SMS gateway, ntfy, phone call, pager.
none (or unset)	Skip the primary action. Go straight to fallback.

Message body, always these five lines, in this order: